<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0725">
  <Title>A Comparison of PCFG Models*</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Recent work (Johnson, 1998) has explored the performance of parsers based on a probabilistic context-free grammar (PCFG) extracted from a training corpus. The results show that the type of tree representation used in the corpus can have a substantial effect in the estimated likelihood of each sentence or parse tree. According to (Johnson, 1998), weaker independence assumptions --such as decreasing the number of nodes or increasing the number of node labels-improve the efficiency of the parser. The best results were obtained with parent-annotated labels where each node stores contextual information in the form of the category of the node's parent. This fact is in agreement with the observation put forward by Charniak (Charniak, 1996) that simple PCFGs, directly obtained from a corpus, largely overgeneralize.</Paragraph>
    <Paragraph position="1"> This property suggests that, in these models, a large probability mass is assigned to incorrect * Work partially supported by the Spanish CICYT under grant TIC97-0941.</Paragraph>
    <Paragraph position="2"> parses and, therefore, any procedure that concentrates the probability on the correct parses will increase the likelihood of the samples.</Paragraph>
    <Paragraph position="3"> In this spirit, we introduce a generalization of the classic k-gram models, widely used for string processing (Brown et al., 1992; Ney et al., 1995), to the case of trees. The PCFG obtained in this way consists of rules that include information about the context where the rule is applied.</Paragraph>
    <Paragraph position="4"> The experiments were performed using the Wall Street Journal (WSJ) corpus of the University of Pennsylvania (Marcus et al., 1993) modified as described in (Charniak, 1996) and (Johnson, 1998).</Paragraph>
  </Section>
class="xml-element"></Paper>